InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation

  • Lee, Jungmin; 
  • Hong, Seonghyuk; 
  • Lee, Juyong; 
  • Lee, Jaeyoon; 
  • Choi, Jongwon
Citations

SCOPUS

0

초록

We introduce InsideOut, an extension of 3D Gaussian splatting (3DGS) that bridges the gap between high-fidelity RGB surface details and subsurface X-ray structures. The fusion of RGB and X-ray imaging is invaluable in fields such as medical diagnostics, cultural heritage restoration, and manufacturing. We collect new paired RGB and X-ray data, perform hierarchical fitting to align RGB and X-ray radiative Gaussian splats, and propose an X-ray reference loss to ensure consistent internal structures. InsideOut effectively addresses the challenges posed by disparate data representations between the two modalities and limited paired datasets. This approach significantly extends the applicability of 3DGS, enhancing visualization, simulation, and nondestructive testing capabilities across various domains.

키워드

3d gaussian splatting; internal structure visualization; multimodal data integration
제목
InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation
저자
Lee, Jungmin; Hong, Seonghyuk; Lee, Juyong; Lee, Jaeyoon; Choi, Jongwon
DOI
10.1109/ICCV51701.2025.02395
발행일
2025-10
유형
Conference Paper
저널명
Proceedings of the IEEE International Conference on Computer Vision
페이지
25820 ~ 25830